Should we always calculate the z in a confidence interval as 1 - (alpha/2)?

I’m currently beginning my studies in statistics and all of the examples of confidence interval questions I studied used (let’s assume a 95% confidence interval) as a z formula z = 1 - (0.05/2), which would result in 0.975 and then using a z-table in 1.96. The thing is, is the alpha always divided by 2 or are all the examples I studied using a two sided distribution?

Cross Validated Asked on November 14, 2021

Yes, it is because you're doing two-sided testing.

When you do two-sided testing, you have to allocate probability to both tails. You pick $$0.975$$ because $$2.5%$$ goes up high, and $$2.5%$$ goes down low.

Answered by Dave on November 14, 2021

Related Questions

A tail bound for an unknown distribution via sampling

1  Asked on February 22, 2021 by bashir

Negative Sampling in Word2Vec – Embedding Vector / Amount of Samples

0  Asked on February 22, 2021 by maxbit

NxN- fold cross validation

1  Asked on February 21, 2021 by tauling

Compare regression coefficients within the same model

2  Asked on February 21, 2021 by shenflow

How to predict an event for different time intervals and compute score?

1  Asked on February 21, 2021

What are arguments against using the (log-)likelihood as a loss function?

1  Asked on February 21, 2021 by joel

How to interpret a ROC curve?

5  Asked on February 20, 2021 by gnal

Minimum sample size per cluster in a random effect model

2  Asked on February 20, 2021 by roccer

Outlier detection for a univariate categorical variable?

3  Asked on February 20, 2021 by abdu

COVID-19: Individual level, cross-country Panel dataset. Which method to use?

0  Asked on February 20, 2021 by user307627

Partial dependence plot, GBM multinomial

1  Asked on February 19, 2021 by daniel-l

Why is it ok to remove variables with low variance from a dataset

0  Asked on February 19, 2021 by amnon

In a predefined (but realistic, and explaining) example, what $p(x)$ should be in a variational autoencoder?

1  Asked on February 19, 2021 by gerg-horvth

Examples of Bayesian and frequentist approach giving different answers

7  Asked on February 19, 2021

Choice of covariate under Independent Hypothesis Weighting (IHW)

0  Asked on February 19, 2021 by kyle-pena

What is the advantages of Wasserstein metric compared to Kullback-Leibler divergence?

5  Asked on February 19, 2021 by thomas-fauskanger

Regression Analysis with a Census or All Observations (Not a Sample)?

1  Asked on February 18, 2021 by statcurious

Compare the results of two canonical correlation analyses (CCA)

1  Asked on February 18, 2021 by forlooper

Why doesn’t the optimizer just look for stationary points of the loss function?

1  Asked on February 18, 2021 by borut-flis

Statistical analysis for comparing expertise levels between 3 groups

0  Asked on February 17, 2021 by kaaren0111