#Janice age regression

[eflen-n-reegee]

Caregiver Electric Mayhem Headcanons (The Muppet Movie)

Dr. Teeth

His wardrobe is a symphony of chaos, and you’re always welcome to partake. He’s happy to loan you any of his clothes, or take you shopping to create your own crazy outfits. A kiddo as amazing as you was born to stand out!

He often goes on complimentary tangents with flowery (and possibly made-up) words. He loves talking, and he loves you; so talking about you can last for ages.

He loves to sit and color with you, or help you repaint your room, or use face paints on you… Art is something he really enjoys, and he’s always excited to share it with you.

Slow, quiet music isn’t really his scene, but he’ll play some softer tunes if you need help falling asleep. (And if you want something loud and proud to help you wake up, he’s got ya covered!)

He and the others put together a “Cool Kid’s Corner” on the tour bus so you ride along with them. (Dr. Teeth totally got you a beanbag chair so you can travel in maximum comfort.)

Floyd

Spoils the HECK out of you. (Nothing’s too good for his kiddo!) Often, you don’t even need to ask for what you want; he just knows somehow.

Also, ALL the compliments. Everything you do, you do well; anything you wear, you look great in; every time you mess up, you mess up with style. Seriously, your self-esteem may never be higher than it is while you’re with Floyd.

He occasionally loans you his jacket ‘cause he thinks you look adorable wearing it. (And you do.)

As the main songwriter of the band, you can bet he writes songs about you on occasion. Anyone who knows you can tell when a song is about you because he’ll incorporate things you frequently say or do, things you enjoy, and general descriptions of you.

Maybe it’s because of his songsmith skills, but he is great at telling you bedtime stories. He usually tells you the classics, but he describes them so uniquely you often feel like your hearing something brand new.

Janice

She prefers to stick to organic foods for herself, so she is super on top of your food preferences and restrictions. (She also tries to encourages you to eat healthy, but she’ll never force you; it’s a free country after all.)

She likes to wear a bit of makeup, and she loves to help you put on makeup if you choose to wear it. You look fantastic with or without it, of course, but getting extra fancy is always fun.

Whatever age you regress to, Janice treats you a little younger. She can’t help herself - you’re just so cute, she just HAS to baby you!

One of her favorite activities to do with you is tie-dye clothes - or stuffed animals! She has a number of methods for making amazing patterns, and she loves to see you wearing the things you create.

She is super encouraging of everything you do. She’s always trying to boost your confidence.

Animal

In a lot of ways, he’s like a big dog. He’s wild, excitable, and incredibly protective of you. No person will ever bother you ever again, and anything inanimate that upsets you (thunder, darkness, bugs) is gonna be growled at.

He has the highest energy levels of anyone in the band. Any time you want to play, he’s ready! He especially loves games where he gets to chase after you.

Animal is very rough-and-tumble and likes to wrestle, but he’s always very careful not to hurt you.

Sometimes kids just want to be destructive. Maybe you’re upset about something; maybe you’re overly excited. Whatever the reason, Animal is ALWAYS ready to help you break things.

… And sometimes kids just want to sit quietly. Animal isn’t as good at just hanging out, but for you, he’s willing to try.

Zoot

He’s the chillest member of the band. He never pushes you to talk or do things; if you just want to sit on the couch in silence for hours, he’s right there with you.

(Similarly, if you want to hang out and watch movies, he’s always up for that. He really enjoys watching things you enjoy, even if he sometimes spaces out.)

Zoot can be forgetful at times, but he always remembers the really important things. He never forgets what kinds of things upset you, what allergies you have, or your favorite pet names.

If you need to vent, he’s always ready to listen. He’s one of the best people to talk to; he never interrupts and doesn’t offer any advice unless you really want it.

He’s tremendously patient. If you’re struggling to learn something new, he’ll remind you a hundred times without getting frustrated. If you’re throwing a tantrum, he’ll wait you out without ever losing his cool. He’s never gets annoyed no matter what you do or don’t do.

[the-crittercorner]

I'm a bit late to posting this but for my birthday I got a peace puppy! I had been looking for one without a code to go with my virtual puppy and we'll here we are! This is Janice (she/her) shes a crystal girly and an artist can't wait to see what adventures her and the other webkinz pups get up to!

[pinkarsonist0]

Last night, I had a dream where a new batch episodes of The New Norm aired, and in one of those episodes Chloe stands up to Norm when he's being a piece crap and out of impulsive rage she locks Norm out the house to give her space.

But in that same episode, it was revealed that Chloe age regresses, Chaz and Janice were her caregivers, so I got minor Chloe x Chaz as a treat. And no, Norm doesn't know about her regression, and I like to think it stayed that way.

Fanfic writers do what you want with that, I guess.

[cosmogify]

Friday Night Fightin - Pico Reference Sheet

Got a bit lazy with this one but it was still fun pfft, here's the last of the fightin RGB trio, Derrick the Dino bodyguard.

Friday Night Fightin BF Ref Sheet Friday Night Fightin GF Ref Sheet

Name: Derrick Dino

Nickname: Pico, Dee, DD

Birthday: 30th December

Age: 26

Orientation: Biromantic Aceflux

Species: Dino creature (yes)

Height: 5'6ft

Weight: 185 lbs

Voice: Riikami but a bit more guttural kekw

Relationship Status: Dating

Family: John Dino (fightin!Tankman)

Partners: Stacie Daemon (fightin!GF), Mikey Angel (fightin!BF)

Friends: Neena Arachnes (fightin!Nene), Darnell Phoenix (fightin!Darnell)

Acquaintances: Skid Skelly and Pump Pumpkin (fightin!SkidandPump), Marco Daemon (fightin!DaddyDearest), Janice Daemon (fightin!MommyMearest)

Enemies/Rivals: Darnell Phoenix (fightin!Darnell), Ayumu Obake (fightin!Senpai)

Personality: A taciturn and seemingly distant young man with a permanently annoyed face, but acts more of a tsundere when shown affection by other people, especially from his partners. He doesn't want to admit, but he can be quite the loverboy and would occasionally flirt with either Stacie or Mikey (mostly Stacie, Mic is as oblivious as a rock but that's part of the charm) from time to time. When fighting however, he would become a lot more trigger happy to shoot a bullet through your skull and acts a lot more aggressive and expressive. He takes his role as a bodyguard half seriously at first, but he gets more invested in his job overtime as he fell in love with Stacie and later Mic.

Personality flaw: Whenever something irks him, he becomes more antsy, impulsive and hot headed about it. He has a very hard time trusting others around him, especially strangers and people he doesn't like and would be more protective of his partners. Loud screams and epileptic lights reverts his brain back to the time of the school shooting during middle school, causing himself to hyperventilate and huddle in a dark area or a corner and will instinctively shoot anyone that would suddenly touch him. He's slowly getting better from it, though there are times he would regressed back progress if the trigger was severe.

Likes: Vocaloid, Crunk hip hop, working out at the gym, spending time with his partners, card games, initiating fights, compete in tournament battles with Mic, showing his muscles and physical flexibility, but likes to wear baggy clothing when spending alone time with Mic, hamburgers, Pepsi, gun shooting practice, firearms in general, showing and giving affection his partners (despite how hesitant he may be).

Dislikes: Stacie's parents (doesn't show it), loud screams and flashing lights, green tea, coke (joking), his impulsivity, being vulnerable, waiting.

Powers: Claw slashes, fists and dropkicks (basic combo attacks), Bazooka missiles! (Heavy combo attacks), Air dash and wall climb (launches himself in the air with a bazooka as a double jump), Bullet spray (fires his Uzi's at a certain direction), Claws strike (Pivots and slashes with all three claw hands at the target, Strength boost (Temporarily makes his attacks stronger and faster), Jelly Bones (Is able to contort and bend his body with relative ease).

Backstory (summary): John Dino was definitely a strict father, being a retired military officer and all. Now he works under the Daemon family as a bodyguard and brought him along to get life and work experience at a young age, which was when he met Stacie. At first he didn't really like her, but that soon change down the line as he would spend days together with her, finding her nice to be around now. Since Stacie was still homeschooled he would the mornings and afternoons at his own middle school with his other friends Neena and Darnell who would also visit Stacie from time to time when walking home together. One day without warning, all hell broke loose at the school. Fellow students were screaming and dying as light bulbs would break one by one from the stray bullets, Derrick think of anything else other than to survive (I will not go further than that, I'm not good at writing devastating scenes). Years passed, the memory was still fresh in his mind but kept suppressing it even during college years, and even after meeting Mic. However, he's finally trying to make a change to it as of late, maybe it won't be so bad. So long as he's with his loving partners, he'll definitely be fine.

Additional notes:

He's farsighted so he would wear reading glasses when needed, but rarely wear them.

Man is a love bug in denial, cuddle him and he will wrap around in his appendages in seconds.

Wears silver ear piercings, usually the thicker kinds

Likes contorting his body in odd places to spook his partners and friends.

Strangely likes to hang upside down when bored.

[strangehoot]

New Post has been published on Strange Hoot - How To’s, Reviews, Comparisons, Top 10s, & Tech Guide

New Post has been published on https://strangehoot.com/how-to-do-regression-analysis-in-excel/

How to Do Regression Analysis in Excel

Regression Analysis is a technique to forecast the relationship between data variables of entities such as customers, orders, transactions etc. These are the parameters based on which business decisions can be taken for sales, finance and marketing operations. To understand this in a simpler way, let us take some examples.

Example 1 – Risk Analytics in Retail Banking

Credit risk scores of customers are built by the banking industry to predict the customer’s delinquency behavior and to evaluate credit worthiness of each customer while processing loan applications.

Example 2 – Marketing Analytics in eCommerce

To predict customer’s buying patterns based on the customer’s past transactions from an online portal. The e-commerce industry is highly competitive so they use analytics to predict customer’s purchasing patterns.

Example 3 – Pricing Analytics in Stock Market

Stock brokers and investors use analytics to forecast stock pricing based on the past 52-week pricing trend and many other parameters. The analytics helps them to make the decisions on buying or selling the stocks based on the future pricing predictions.

Example 4 – Behavioral Analytics in Human Resource Industry

Human resource departments / companies use analytics to predict employees’ behavioural patterns that will enable them to decide the increment or promotion to be given on a yearly basis.

Regression Analysis Basics

Before we go for how to do regression in Excel taking a case study, let us understand the dataset and its components.

Population vs. Sample

Population is referred to as all members of a defined group that are considered for studying information on data driven decisions. For example – Current inflation rates of EU countries.

Sample is a part of “population”. It can be biased or unbiased. For example – Current inflation rates of EU countries having per capita income < 50000 EURO per annum.

Types of Data Variables

The below diagram shows types of data variables under each category.

Data Snapshot

The table below gives an example of data snapshot with different data variables.

#Cust.NameCust. IDNo.Of credi cardsGenderMaritalStatusAgeAnnualSalaryMonthly Credit Card Usage1Josh1116695FNeverMarried4388,001Low2John2231126MMarried24592,330Low3Alen1891234MDivorced50272,304Low4Chaya1716903FMarried37140,400Low5Dandre166256MNeverMarried23105, 234Low6Justin1491717MDivorced34358,534Low7Neil1692545MMarried36510,321Low8Emily1497712FNever Married26164,732Low9Janice1756462FMarried35103,345Low10Farhan1706394MNever Married63724,788Low11Tony1131363MMarried70105,450Low

Let us understand the data variables available in the above table.

#Cust.NameCust. IDNo.of credit cardsGenderMaritalStatusAgeAnnualSalaryMonthly Credit Card Usage–––Numerical (Discrete)Categorical (Binary)Categorical (Nominal)Numerical (Discrete)Numerical (Continuous)Categorical (Ordinal)

Summarizing Data

The next step is to summarize data in a presentable format that will give the report on which analysis can be done. The ways to summarize the data are as follows:

Frequency Distribution – this is a simple way of counting distinct discrete values. For example – Number of credit cards owned by 3000 customers as sample data. Can be shown as tabular format or as a graph using Excel.

Steps to do this in Excel:

Go to the Data tab in your Excel Worksheet. 

Click Advanced. The dialog is shown

Go to the Number of Cards column. Sort them into ascending order of values.

Insert the formula in # of customers to set the frequency.

You will get the values as below.

Go to the Insert tab. Click the Column icon. Select the 2-D Chart.

The chart will be generated and shown as below.

Grouped Frequency Distribution – this is a method to summarize discrete variables having a large number of observations and range of values. For example – Number of customers falling under different salary ranges or groups.

Follow the steps in Excel as per instructions given in the screen below.

Cumulative Frequency Distribution – this is obtained by accumulating the frequencies to give the total number of observations up to and including the value or group in question. Illustration as per screen below.

Steps to calculate the cumulative frequency distribution are give in the screen below.

Stem Leaf Diagram – this technique is used in a limited set of data. For a large set of data, this method is not used. Example : Given age of 20 individuals in years. 

Line Plots – this technique is also not suitable for a large set of data. It is not extensively used in the industry. Example: Given test scores of 20 students.

Measure of Central Tendency – Median

The central tendency measure is robust to the effects of extreme observations. 

The median is a value, which splits the data set into two equal halves. Example – Calculate the median for a sample of 3000 individuals having credit cards along with demonstration of extreme observations.

Measure of Central Tendency – Mode

It is the value which occurs with the greatest frequency or the most typical value. For Example, finding the mode for a sample of 3000 individuals having credit cards. Excel has an in-built function “Mode” for granular data. For summarized data, it can be found easily by visual inspection. Illustration as below.

Measure of Spread

The different measures of spread are – 

Variance and Standard Deviation – below screen shows how to calculate the values.

The Range – It is a very simple measure of spread defined, as its name suggests, by the difference between the largest and smallest observations in the data set.

The Inter quartile range – the quartiles divide a set of data into four quarters. They are denoted by Q1, Q2 and Q3. Q1 is called the lower quartile and Q3 the upper quartile. Following image shows how to calculate Inter quartile Range for a sample of 3000 individuals having credit cards.

Symmetry and Skewness of data

It represents the shape of the distribution of a dataset, that is, whether it is symmetric or skewed to one side or the other.The approximate shape of a distribution can be determined by looking at a  histogram. The below diagram shows mean, median, mode and variance for symmetric and skewed data.

Tabular representation of data as shown below.

After evaluating the dataset by the above measures and techniques, a regression analysis can be conducted. Now, the question is which type of regression model is required for predictions.

The next section describes the measures that will state the relationship between the data variables and determine how strong the relationship is between identified variables.

Regression Analysis Models

Following are different techniques or formulas that are used to do regression analysis. These techniques are nothing but different formulas or equations that are used to determine the relationship between X and Y variables.

Covariance and correlation coefficient are the measures used in regression analysis. 

Covariance is a measure that helps to find out the direction of relationship between x variable and y variables. In simple terms, what happens to y when x increases or decreases. 

Following equation is used to determine the covariance measure.

Correlation coefficient is the measure that tells how strong the linear relation is between X and Y variables. It is termed as r value that determines the quality of a model. The parameter is represented by p or r values. 

Population correlation is denoted by ρ (rho)

Sample correlation is denoted by r.

Following equation is used to determine the correlation coefficient measure for population data.

In real life data analytics, the correlation measure is calculated on sampling distribution. There are a couple of reasons why the sampling is used for analytics.

The physical impossibility of checking all items in the population.

The cost of studying all the items in a population.

The sample results are usually adequate.

Contacting the whole population would often be time consuming.

Features of ρ and r

Unit free and ranges between -1 and 1

The closer to -1, the stronger the negative linear relationship

The closer to 1, the stronger the positive linear relationship

The closer to 0, the weaker the linear relationship

Negative Linear Relationship 

Positive Linear Relationship 

Relationship Not Linear

No Relationship

Tools used to do Regression Analysis

Following software tools are the most used in performing Regression Analysis. The oldest tool is Microsoft Excel. 

SAS (www.sas.com/)

SPSS (http://www-01.ibm.com/software/analytics/spss/ )

R (http://www.r-project.org/)

Microsoft Excel (http://office.microsoft.com/en-in/)

As the spectrum of analytics is widened, dataset volume has increased, the data scientists have started using Python.

We will see a case study to run regression analysis in Excel.

Case Study

An Auto Insurance company having the data of “Loss” amount and policy related information. The company wants to know the factors responsible for losses in multivariate fashion using a regression model.

Prior to running the regression model, following things needs to be in place.

Variable identification –

Identifying the dependent (response) variable.

Identifying the independent (explanatory) variables.

Variable categorization (e.g. Numeric, Categorical, Discrete, Continuous etc.)

Creation of Data Dictionary

Response variable exploration

Distribution analysis

Percentiles

Variance 

Frequency distribution

Outlier treatment

Identify the outliers/threshold limit

Cap/floor the values at the thresholds

Independent variable analyses

Identify the prospective independent variables (that can explain response variable)

Bivariate analysis of response variable against independent variables

Variable treatment /transformation

Grouping of distinct values/levels

Mathematical transformation e.g. log, splines etc.

After performing the above data related activities, the last step is iterative in terms of running the regression.

Fitting the regression (first time)

Check for correlation between independent variables

This is to take care of Multicollinearity

Variable selection

Check for the most suitable transformed variable

Select the transformation giving the best fit

Reject the statistically insignificant variables

Fitting the regression (iteration)

Analysis of results

Model comparison

Model performance check

Actual vs Predicted comparison

Steps to do regression analysis in Excel

We will perform the following steps in Excel with reference to the case study explained in the section above.

Data Analysis

Step 1. Snapshot of Data and Data Description

The above data contains policy holders’ and loss amount information (variables)

Policy Number

Age

Years of Driving Experience

Number of Vehicles

Gender

Married

Vehicle Age

Fuel Type

Losses (Dependent/Response Variable)

A Data Dictionary is formed as below.

Sl #Variable NameVariable DescriptionValues StoredVariable Type1Policy NumberUnique Policy NumberUnique value identifying the policyIdentifier2AgeAge of Policy holder16, 17,…,70Numerical (Discrete)3Years of Driving ExperienceYears of Driving Experience of the Policy holder0,1,….,53Numerical (Discrete)4Number of VehiclesNumber of Vehicles insured under the policy1,2,3,4Numerical (Discrete)5GenderGender of the Policy holderF, MCategorical (Binary)6MarriedMarital status of the Policy holderMarried, SingleCategorical (binary)7Vehicle AgeAge of vehicle insured under the policy0,1,…,15Numerical (Discrete)8Fuel TypeFuel type of the vehicle insuredD, PCategorical (Binary)9LossesLoss amount claimed under the policyRange: 13- 3500Numerical (Continuous)

Step 2. Frequency Distribution – Loss amount

Step 3. Calculate Capped Losses using grouped frequency distribution

Step 3. Perform variable analysis in Excel. The first bivariate profiling we will do for Age vs. Capped Loss for policies.

Step 4. The second bivariate profiling we will do for Years of Driving Experience vs. Capped Loss for policies.

Step 5. The next bivariate profiling we will do for Gender vs. Capped Loss for policies.

Step 6. The next bivariate profiling we will do for Marital Status vs. Capped Loss for policies.

Step 7: The next bivariate profiling we will do for Vehicle Age vs. Capped Loss for policies.

Step 8: The next bivariate profiling we will do for Vehicle Age Band vs. Capped Loss for policies.

Step 9: The next bivariate profiling we will do for Vehicles vs. Capped Loss for policies.

Step 10: The next bivariate profiling we will do for Fuel Type vs. Capped Loss for policies.

Preparing Excel for Regression Analysis

Step 1: Open Office icon from the toolbar.

Step 2: Go to Excel Options.

Step 3: Click Add-Ins.

Step 4: From the Manage drop-down, select Excel Add-ins.

Step 5: Select the Analysis Toolpak check box and the Solver Add-in check box.

Step 6: Select the Data tab. Click Data Analysis. 

Step 7: In the Data Analysis dialog box, click Regression.

Step 8: Select the data cell reference range. Click OK.

Step 9: See the summary results as below.

Step 10: Picking up the variables based on the following activities.

We will perform the following tests to select by running :

Multicollinearity

Banding of variables

Statistical significance of variables tested

List of independent variables:

Age

Age Band

Years of Driving Experience

Number of Vehicles

Gender

Married

Vehicle Age

Vehicle Age Band

Fuel Type

“Age” and “Years of Driving Experience” are highly correlated (Correlation Coefficient = 0.9972). We can use either of the variables in regression.

Fit two separate models using either of the variables one at a time. Check for goodness of fit (R2 in this case).  The variable producing higher R2 gets accepted.

Age

Regression Statistics (Age)Multiple R0.475766R Square0.226354Adjusted R Square0.226303Standard Error201.2306Observations15290

Years of Driving Experience

Regression Statistics(Yrs Driving Experience)Multiple R0.475273R Square0.225885Adjusted R Square0.225834Standard Error201.2916Observations15290

R2 for Age > R2 for Years of Driving Experience

Reject Years of Driving Experience

Banding of Variables

Investigate whether to use “Age” or “Age band”

Fit regression independently using “Age” and “Age Band”

Before fitting regression, “Age Band” needs to be converted to numerical form from categorical. Replace “Age Band” values with “Average Age” for the particular band.

Age BandSum of Age# PoliciesAverage Age16-25      93,770.0     4,563.0                 20.6 26-59    270,793.0     6,384.0                 42.4 60+    282,636.0     4,343.0                 65.1 

Regressions results using “Age” and “Average Age”

Regression Statistics (Age)Multiple R0.475766R Square0.226354Adjusted R Square0.226303Standard Error201.2306Observations15290

Regression Statistics (Average Age)Multiple R0.509969R Square0.260068Adjusted R Square0.26002Standard Error196.7971Observations15290

R2 for Average Age > R2 for Age

Select “Average Age”

Investigate whether to use “Vehicle Age” or “Vehicle Age band”

Fit regression independently using “Vehicle Age” and “Vehicle Age Band”

Before fitting regression, “Vehicle Age Band” needs to be converted to numerical form from categorical. Replace “Vehicle Age Band” values with “Vehicle Average Age” for the particular band.

Vehicle Age BandSum of Vehicle Age# PoliciesAverage Vehicle Age0-5                            9,229                 3,688 2.506-10                          44,298                 5,523 8.0211+                          78,819                 6,079 12.97

Regressions results using “Vehicle Age” and “Average Vehicle Age”

Regression Statistics (Vehicle Age)Multiple R0.289431325R Square0.083770492Adjusted R Square0.083710561Standard Error218.9903277Observations15290

Regression Statistics (Average  Vehicle Age)Multiple R0.303099405R Square0.09186925Adjusted R Square0.091809848Standard Error218.0203272Observations15290

R2 for Average Vehicle Age > R2 for Vehicle Age

Select “Average Vehicle Age”

Now, we have identified the variables that can be used in fitting the regression model.

Age Band in the form of “Average Age” of the band (selected out of “Age” and  “Age Band”). Also got selected over “Years of Driving Experience”.

Number of Vehicles

Gender

Married

Vehicle Age Band in the form of “Average Vehicle Age” of the band (selected out of “Vehicle Age” and  “Vehicle Age Band”). 

Fuel Type

Step 11: Categorical variables to be converted to their numerical equivalent (0,1)

Gender (F = 0 and M = 1) 

Married (Married = 0 and Single = 1)

Fuel Type (P = 0, D = 1)

Snapshot of the final data on which we will run the multivariate regression.

Step 11: Run Regression. 

Summary of Output

SUMMARY  OUTPUT  Regression StatisticsMultiple R0.865972274R Square0.749907979Adjusted R Square0.749809794Standard Error114.4310136Observations15290ANOVA dfSSMSFSignificance FRegression6600073213.5100012202.37637.7510880Residual15283200122584.413094.45688Total15289800195798    CoefficientsStandard Errort StatP-valueLower 95%Upper 95%Lower 95.0%Upper 95.0%Intercept624.565295.29192118.022330.00000614.19249634.93809614.19249634.93809Avg Age-5.559740.06546-84.938890.00000-5.68804-5.43144-5.68804-5.43144Number of Vehicles0.178750.970390.184200.85386-1.723332.08082-1.723332.08082Gender Dummy50.883261.8908126.910840.0000047.1770554.5894747.1770554.58947Married Dummy78.398371.9214840.801060.0000074.6320482.1646974.6320482.16469Avg Vehicle Age-15.142200.26734-56.639870.00000-15.66623-14.61818-15.66623-14.61818Fuel Type Dummy267.935592.7484597.486140.00000262.54830273.32287262.54830273.32287

Results Interpretation

Significant Test

Significance test of coefficients based on Normal distribution

H0: b is no different that 0 (i.e. 0 is the coefficient when the variable is not included in regression)

H1: b is different than 0 

Test statistic, Z = (b-0)/σ  (at 95% two tailed confidence interval, Z = 1.96)

Confidence interval = (b – 1.96 * σ, b + 1.96 * σ)

For the variable to be significant, the interval must not contain “0”.

Example1: Avg Age.

Confidence interval = (-5.560-1.96*0.065, -5.560+1.96*0.065) = (-5.688, -5.431)

No zero in the interval. Hence, significant.

Example2: Number of Vehicles

Confidence interval = (0.179-1.96*0.970, 0.179+1.96*0.970) = (-1.723, 2.080)

Zero is present in the interval. Hence, insignificant.

Summary output after removing insignificant variables.

Predicted Losses = 625.004932715948 – 5.5596551344537 * Avg Age + 50.8828923910091 * Gender Dummy + 78.4016899779131 * Married Dummy -15.1420259903571 * Avg Vehicle Age + 267.935139741526 * Fuel Type Dummy

Interpretation

Takeaway

Running regression in Excel gives you more confidence on your model as you are running each step manually. It is a time consuming and lengthy process, but you get to learn more on datasets and output summary. Other tools such as R, SAS and Python give you quick results but you will not be able to know the algorithm behind the code that is executed and have given you the results.

[weerd1]

Star Trek TOS Rewatch Log, Christmas Binge Entry, Stardate 1712.25: Missions Reviewed: "The Way to Eden," "The Cloud Minders," "The Savage Curtain," "All Our Yesterdays," and "Turnabout Intruder."

To Celebrate Christmas, rather than burn the Yule Log, we burned through the rest of the Captain's Log and completed our rewatch of the Original Series.  This will be a long one as I review FIVE episodes, and then give some overall thoughts on what impressions I have of the series in order in the modern day stand out for me.  Thank you all who have read these and joined us vicariously though this endeavor, and I appreciate your tolerance on this last long one!

"The Way to Eden" held up better for me than it did for Jennifer.  The Enterprise is in pursuit of a stolen space cruiser, and one of the criminals is a diplomat's son.  The six people saved before the ship is destroyed by the strain of trying to escape the Enterprise are the followers of Dr. Sevrin, and a very heavy handed allegory for the counter-culture movement of the late 1960s. Sevrin (played by Skip Homeier, whom we also saw as a guest star in "Patterns of Force") it turns out is also the carrier of a disease that he claims has been caused by humanity's dependence on technology, so he is leading his "enlightened" crew in search of a planet he claims to be Eden, a paradise where man can return to their natural state. The matter is complicated by the fact one of the space hippies is an old girlfriend of Chekov who had dropped out of Starfleet Academy.  She and the others take advantage of goodwill, and seize control of the Enterprise; Eden however proves to be more dangerous than they thought, as the plantlife in the planet-sized garden are all acidic and poisoned. The commentary is a little mixed giving some sympathy to those who want to seek unity outside of a technological culture, but Sevrin is also presented as insane and using the others to his advantage.  The fact they conspire to seize the ship and Sevrin plans to kill the Enterprise crew makes it difficult to sympathize as well.  Irina (Chekov's ex, played by Mary Rapalye) in the end though, even after Sevrin has killed himself to keep from leaving the poisoned Eden, still plans to find some kind of simpler existence, and Chekov wishes her well.  The repeated musical numbers were actually written and performed by Charles Napier who plays Adam, and would later go on to play the leader of the cowboy band chasing The Blues Brothers and a US military officer in the Deep Space Nine episode "Little Green Men."  Spock understanding where the hippies are coming from and entering a jam session with them is actually pretty cool.  I thought so...Jennifer was not as kind in her opinion!

"The Cloud Minders" seems to owe a lot to the classic morality tale, Fritz Lang's 1927 film "Metropolis." The Enterprise must secure a mineral from planet Ardana, whose culture is divided into the artistically minded ruling class in a Cloud City (eat your heart out, Bespin) while the working class Troglytes live on the ground and do all the mining and manual labor.  Kirk and crew arrive while the planet is having social disruption as the ground dwellers are beginning to demand rights.  The rulers say they are incapable of handling such consideration due to their limited intelligence, but Spock proves their angry state is actually caused only by the gas given off by the "Xenite" they mine. Indeed, the revolution as only come now because a few Troglytes were allowed to live in the city and were no longer affected.  It's a little unclear how a planet so socially awful in its division of labor was allowed into the Federation, but Kirk is just as willing to ignore not interfering with a Federation member as he is with the Prime Directive.  After some abduction and fisticuffs, the Xenite is secured, the Troglytes are provided masks to counter the effects of the gas, and though they are ticked off, the rulers are willing to at least negotiate.  This episode, like many, feels more timely than a 50 years old TV show should in it's discussion on the treatment of the labor class and how benefits are distributed in society.  From a Trek perspective, I found the visors the miners wear are remarkably similar to what Khan is wearing when recovered in TWOK. This was a David Gerrold (The Trouble with Tribbles) story, though he was displeased with some of the rewrites, specifically the gas affecting the miners; he intended the rulers to have much less reason to establish their superiority.  It would be interesting to see a full production of his original script in some form.

Not holding up anywhere near as well is "The Savage Curtain." Investigating what should be a molten planet, the Enterprise finds an unexpected area of livable surface...and Abraham Lincoln.  Yep.  It turns out the Excalbians are more silicon based lifeforms who have taken Kirk and Spock, pulled heroes and villains from their minds and will now make the "good" and "evil" fight it out for the amusement of the other living rocks on the planet.  The episode, as fairly awful as it is, does contribute three really important ideas introduced to Trek history: First, we see taken from Spock's mind Surak, the father of Vulcan philosophy.  He continues to maintain his pacifism as well, refusing to fight the "evil" side, though he is killed for it.  We also get our first look at Col. Greene, who was a purist dictator from the early 21st Century.  This character will appear again in "Enterprise" where there are still xenophobic, racist assholes following his example into the 22nd Century. I would like to think Eugenic purists would not really be an issue in either the 22nd or for that matter the early 21st Century, but again, this 50 year old show proves to be more relevant that it should.  Finally, we also are introduced to "Kahless the Unforgettable," who started the Klingons off.  He will of course be mentioned throughout future Trek's run, even being cloned and brought back to rule the Empire in "TNG," and cited as the reason T'Kuvma tries to unite the Klingon houses and declares war on the Federation in "Discovery." Here he exhibits the ability to perfectly mimic voices; whether that's a attribute of Kahless or an artifact of being artificially produced is unclear. Most of this episode is fairly useless, but fleshing out the Trek universe is a worthy achievement.  They do however refer to Lincoln as being from "300 years" in the Enterprise's past, which would again set the series in the 22nd century. As I have said before, the actual dates of the series will not be solidified until the end of TNG's first season, which gives a concrete year or 2364. All other Trek calendar dates in the future are extrapolated from that.

"All Our Yesterdays" has long been one of my favorites. The Enterprise has come to observe a supernova over the planet Sarpeidon. There had been a significant population there, but they seem to all be gone, despite the fact that the planet has not developed interstellar travel. Kirk, Spock, and McCoy find that using a special "library," the population has scattered themselves through Sarpeidon's past.  Through accident, Kirk finds himself stuck in a period similar to England's 1600s, where he is accused of being a witch. Spock and McCoy are thrown 5000 years back into Sarpeidon's ice age where they find the beautiful Zarabeth, who has been imprisoned here in isolation. Being "unprepared" for the past though causes Spock to begin acting like Vulcans of the past, eating meat, and seducing Zarabeth. A complaint I have seen about this episode is that McCoy does not similarly regress, but he does seem to me to be even more irascible than he usually is.  I give affected Spock props though for FINALLY standing up to all the rampant racism McCoy has a tendency to throw at him, threatening to choke the Doctor after one too many "pointy eared" comments.  Good on you Spock.  Guest star Mariette Hartley is really good here, and you feel her loneliness; she WAS prepared and cannot return to the present.  There were actually a couple of novelized sequels to this episode written in the 80s I remember loving, "Yesterday's Son," and "Time for Yesterday." by A.C. Crispin where we find out Spock and Zarabeth had a son, and as they play out "Zar" will become an architect of Sarpeidon's development.  Speaking of that development, it seems odd that this world has not developed space travel, but has developed time travel.  I kind of want to hear more about that!

And then, there is the last episode of TOS, both to air and to be filmed, "Turnabout Intruder." Kirk and crew visit a scientific expedition led by Janice Lester, which seems to have befallen great tragedy.  All is a ruse though as Lester, yet ANOTHER one of Kirk's ex girlfriends, as found ancient technology that allows her to switch her life essence with Kirk and take over his body. It seems that she has resented his life in Starfleet and felt denied opportunity because she was a woman, and has decided she will take what is owed her. As Kirk, Lester proves a terrible commander, leading to Scotty describing the captain as screaming in "red-faced hysteria." It's east to kind of retcon some of the information given here and say that it's just Lester that was mad, hence her inability to cope in command, and that when she says "there's no room in your world of starship captains for women," that she is talking about Kirk rebuffing her rather than the idea that women can't command starships.  True, even in "The Cage," the first officer was a woman, and one would assume she could command in Pike's absence, and perhaps Roddenberry (who actually wrote this one!) was commenting on the network would not buy a woman in the position, but this one really does seem to come from a chauvinistic position. Kind of a sad way for the show to leave the air. Shatner during this episode was apparently suffering a strong fever and flu, but he gives his all as Lester, while Sandra Smith as the physical Janice Lester does a credible job as Captain Kirk trapped in her body.  For a really in depth look at the filming of this episode, try and find the 1975 book "Star Trek Lives!" where superfan Joan Winston spent six days on the set while this one was filmed. 

And, from here there really is no "NEXT VOYAGE." "Turnabout Intruder" aired on June 3rd, 1969. The show had almost been cancelled after season two, but a letter-writing campaign brought it back for a third season.  That helped them meet the magic number of episodes to enter syndication, and it was there that Trek truly found its audience.  In its original run, TOS never broke the top 25 shows ratings wise, but the next year, the Nielsen company added demographics to the way they analyzed data. Data shows that Trek would have been highly rated for the coveted 18-25 age market, and might have changed its fate. As it was, the syndication became incredibly popular, and led to the 1973 animated series.  Another series "Star Trek Phase II" was planned for the late 70s, but the success of "Star Wars" turned it into a movie first, and in 1979 we got "Star Trek: The Motion Picture." Despite a lukewarm reaction, Trek was back on people's minds, and obviously it isn't quite gone yet.

A couple of things really stood out for me in this concentrated rewatch: episodes I had dismissed when younger held up for me better as an older man, and indeed only a handful I think earn the label "bad."  (Still looking at YOU, "The Alternative Factor" as the worst, even more than "And the Children Shall Lead!")  So many of the themes of racism and classism, or man being too caught up in his technology can easily be applied today, and despite some VERY 1960s gender politics, the show does make some efforts that were daring at the time; again, in a world where people were debating whether or not Black people should be allowed to go to the same schools, having an African-American Woman play an officer is one hell of a statement, and the show deserves attention half a century later on its own merits.

As a fan, I was really surprised to see how many additional repeat characters there were who almost never get remembered. For the first half of season one, Rand was more of a cast member than Sulu (though we do see her again in TMP, TSFS, TVH, TUC, and on VOY).  In the background we repeatedly saw Leslie and Hadley and Kyle (who does at least appear in TWOK) and Palmer and DeSalle and DePaul; yet, they don't get the recognition I wish they would.  I would love to see further adventures in the Kelvin Timeline rectify that (like they did with Hendorff, known there also as "Cupcake.")

And one final mystery: there are six transporter pads, but only three levers.  HOW DOES THAT WORK???

I again thank any of you who took the time to read through these reviews, and I thank Jennifer, the greatest wife in this or any other Galaxy, for watching with me AND letting me take the time to write each one up.  And I encourage all of you to take a look for yourselves. Despite problems, this show still does have plenty to say, and it has earned its 50+ years of progeny continuing the ongoing mission, and continuing to go boldly.  May the Great Bird of the Galaxy smile on your planet!

Space Hippies!

The Troglytes visors:

Khan’s visor:

SPACE LINCOLN!!!!

Spock and Zarabeth, who are as far as I am concerned parents of Zar of Sarpeidon!

“Red-faced hysteria.”

Images from the incredible Trekcore!

[tumimmtxpapers]

CHL1 hypermethylation as a potential biomarker of poor prognosis in breast cancer.

CHL1 hypermethylation as a potential biomarker of poor prognosis in breast cancer. Oncotarget. 2017 Feb 02;: Authors: Martín-Sánchez E, Mendaza S, Ulazia-Garmendia A, Monreal-Santesteban I, Blanco-Luquin I, Córdoba A, Vicente-García F, Pérez-Janices N, Escors D, Megías D, López-Serra P, Esteller M, Illarramendi JJ, Guerrero-Setas D Abstract The CHL1 gene encodes a cell-adhesion molecule proposed as being a putative tumour-suppressor gene in breast cancer (BC). However, neither the underlying molecular mechanisms nor the clinical value of CHL1 downregulation in BC has been explored. The methylation status of three CpG sites in the CHL1 promoter was analysed by pyrosequencing in neoplastic biopsies from 142 patients with invasive BC and compared with that of non-neoplastic tissues. We found higher CHL1 methylation levels in breast tumours than in non-neoplastic tissues, either from mammoplasties or adjacent-to-tumour, which correlated with lower levels of protein expression in tumours measured by immunohistochemistry. A panel of five BC cell lines was treated with two epigenetic drugs, and restoration of CHL1 expression was observed, indicating in vitro dynamic epigenetic regulation. CHL1 was silenced by shRNA in immortalized but non-neoplastic mammary cells, and enhanced cell proliferation and migration, but not invasion, were found by real-time cell analysis. The prognostic value of CHL1 hypermethylation was assessed by the log-rank test and fitted in a Cox regression model. Importantly, CHL1 hypermethylation was very significantly associated with shorter progression-free survival in our BC patient series, independent of age and stage (p = 0.001). In conclusion, our results indicate that CHL1 is downregulated by hypermethylation and that this epigenetic alteration is an independent prognostic factor in BC. PMID: 28178655 [PubMed - as supplied by publisher] http://dlvr.it/NKlvy7